Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43959
    Prev
    Next
    INDEX
    Explanations

    let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     notwithstanding
    -0.08
    distinct
    -0.07
    ल्या
    -0.07
    othermal
    -0.07
     produzido
    -0.07
     teilweise
    -0.07
     zover
    -0.07
     clip
    -0.07
     disparate
    -0.07
    גר
    -0.07
    POSITIVE LOGITS
     hens
    0.09
     확인
    0.09
    �
    0.08
     피
    0.08
    -moi
    0.08
    告诉
    0.08
     জানান
    0.08
     달
    0.08
    了解
    0.08
    세요
    0.08
    Activations Density 0.005%

    No Known Activations